The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Apr. 11, 2023

Filed:

Jan. 31, 2020
Applicant:

D-wave Systems Inc., Burnaby, CA;

Inventors:

Arash Vahdat, Coquitlam, CA;

Mani Ranjbar, Port Coquitlam, CA;

Mehran Khodabandeh, Coquitlam, CA;

William G. Macready, West Vancouver, CA;

Zhengbing Bian, Burnaby, CA;

Assignee:

D-WAVE SYSTEMS INC., Burnaby, CA;

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06N 3/08 (2006.01); G06N 5/02 (2006.01); G06N 5/04 (2006.01); G06N 3/088 (2023.01); G06N 5/022 (2023.01); G06N 5/045 (2023.01);
U.S. Cl.
CPC ...
G06N 3/088 (2013.01); G06N 5/02 (2013.01); G06N 5/022 (2013.01); G06N 5/04 (2013.01); G06N 5/045 (2013.01);
Abstract

The domain adaptation problem is addressed by using the predictions of a trained model over both source and target domain to retain the model with the assistance of an auxiliary model and a modified objective function. Inaccuracy in the model's predictions in the target domain is treated as noise and is reduced by using a robust learning framework during retraining, enabling unsupervised training in the target domain. Applications include object detection models, where noise in retraining is reduced by explicitly representing label noise and geometry noise in the objective function and using the ancillary model to inject information about label noise.


Find Patent Forward Citations

Loading…